A Review of Anthropic's Global Workspace Paper

·LessWrong··

The below is a public review Anthropic asked me to write for their new global workspace paper. I recommend at least skimming their paper first.TLDR:I think this is a fantastic paper - it presents compelling evidence for some kind of "cognitive space" in models, that is used as a "working memory" for intermediate variables during a forward pass, shows that J-Lens is a useful technique for accessing this space. I believe these key claims.I believe J-Lens will be a useful (but limited) tool in prac...

Read full article →

Related Articles

Malicious Rust crate Arrayref runs a build-time payload
abhisek · Hacker News · 12h ago
AliExpress runs silent WebAudio fingerprinting that breaks Bluetooth multipoint
emctech · Hacker News · 15h ago
Copyright does not protect AI-generated content in EU
u1hcw9nx · Hacker News · 1h ago
Google has stopped pushing Git tags for some Android source code
Animux · Hacker News · 1d ago
Devices with GrapheneOS support should be available in 2027
exceptione · Hacker News · 1d ago